© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11541
    Prev
    Next
    INDEX
    Explanations

    words followed by common prepositions or articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.48
     Перейти
    -1.45
     могут
    -1.36
     bụ
    -1.22
    cerely
    -1.19
     esfuerzan
    -1.17
     häufiger
    -1.16
    𝒐
    -1.15
     sebaiknya
    -1.15
    ứng
    -1.13
    POSITIVE LOGITS
     itself
    1.55
     only
    1.55
     its
    1.52
     even
    1.48
     if
    1.40
    t
    1.37
    Additional
    1.29
     annan
    1.23
    What
    1.23
    c
    1.18
    Activations Density 0.354%

    No Known Activations